Inference API not working properly. Lack of proper modeling file?

#1
by xunkai55 - opened

Hi there,

The inference API in the model card is not working properly. I guess the modeling_llama.py is changed as well. Any possibility to open-source it?

Thanks!

SparseLLMs org

Yes, we change the modeling_llama.py. I can give you the code what we changed.

SparseLLMs org

The original modeling_llama.py :

class LlamaMLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.hidden_size = config.hidden_size
        self.intermediate_size = config.intermediate_size
        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=config.mlp_bias)
        self.act_fn = ACT2FN[config.hidden_act]

    def forward(self, x):
        if self.config.pretraining_tp > 1:
            slice = self.intermediate_size // self.config.pretraining_tp
            gate_proj_slices = self.gate_proj.weight.split(slice, dim=0)
            up_proj_slices = self.up_proj.weight.split(slice, dim=0)
            down_proj_slices = self.down_proj.weight.split(slice, dim=1)

            gate_proj = torch.cat(
                [F.linear(x, gate_proj_slices[i]) for i in range(self.config.pretraining_tp)], dim=-1
            )
            up_proj = torch.cat([F.linear(x, up_proj_slices[i]) for i in range(self.config.pretraining_tp)], dim=-1)

            intermediate_states = (self.act_fn(gate_proj) * up_proj).split(slice, dim=2)
            down_proj = [
                F.linear(intermediate_states[i], down_proj_slices[i]) for i in range(self.config.pretraining_tp)
            ]
            down_proj = sum(down_proj)
        else:
            down_proj = self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))

        return down_proj

We modified it to:

class LlamaMLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.hidden_size = config.hidden_size
        self.intermediate_size = config.intermediate_size
        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=config.mlp_bias)
        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=config.mlp_bias)
        self.act_fn = ACT2FN[config.hidden_act]

    def forward(self, x):
        down_proj = self.down_proj(self.act_fn(self.gate_proj(x)))
        return down_proj

Sign up or log in to comment